RESUMO
The emergence of artificial intelligence (AI) in the medical field holds promise in improving medical management, particularly in personalized strategies for the diagnosis and treatment of brain tumors. However, integrating AI into clinical practice has proven to be a challenge. Deep learning (DL) is very convenient for extracting relevant information from large amounts of data that has increased in medical history and imaging records, which shortens diagnosis time, that would otherwise overwhelm manual methods. In addition, DL aids in automated tumor segmentation, classification, and diagnosis. DL models such as the Brain Tumor Classification Model and the Inception-Resnet V2, or hybrid techniques that enhance these functions and combine DL networks with support vector machine and k-nearest neighbors, identify tumor phenotypes and brain metastases, allowing real-time decision-making and enhancing preoperative planning. AI algorithms and DL development facilitate radiological diagnostics such as computed tomography, positron emission tomography scans, and magnetic resonance imaging (MRI) by integrating two-dimensional and three-dimensional MRI using DenseNet and 3D convolutional neural network architectures, which enable precise tumor delineation. DL offers benefits in neuro-interventional procedures, and the shift toward computer-assisted interventions acknowledges the need for more accurate and efficient image analysis methods. Further research is needed to realize the potential impact of DL in improving these outcomes.
RESUMO
The number one cause of cancer in women worldwide is breast cancer. Over the last three decades, the use of traditional screen-film mammography has increased, but in recent years, digital mammography and 3D tomosynthesis have become standard procedures for breast cancer screening. With the advancement of technology, the interpretation of images using automated algorithms has become a subject of interest. Initially, computer-aided detection (CAD) was introduced; however, it did not show any long-term benefit in clinical practice. With recent advances in artificial intelligence (AI) methods, these technologies are showing promising potential for more accurate and efficient automated breast cancer detection and treatment. While AI promises widespread integration in breast cancer detection and treatment, challenges such as data quality, regulatory, ethical implications, and algorithm validation are crucial. Addressing these is essential for fully realizing AI's potential in enhancing early diagnosis and improving patient outcomes in breast cancer management. In this review article, we aim to provide an overview of the latest developments and applications of AI in breast cancer screening and treatment. While the existing literature primarily consists of retrospective studies, ongoing and future prospective research is poised to offer deeper insights. Artificial intelligence is on the verge of widespread integration into breast cancer detection and treatment, holding the potential to enhance early diagnosis and improve patient outcomes.
RESUMO
ABSTRACT Aim To prepare a consensus document of the cariology contents and competences included in the curriculum for the dentistry degree at Argentine dental faculties/schools Materials and Method Planning the process in stages: Stage 1- Diagnosis of the situation (Google Form) and invitation to participate extended to the 20 academic units that offer dentistry degrees. Stage 2- Assessment process of Content (C) and Competences (I) agreements in the five domains: D1 Basic Sciences, D2 Risk and diagnosis of dental caries, D3 Decision-making for non-invasive treatments, D4 Decision-making for invasive treatment, and D5 Evidence-based cariology at community level. Stage 3- Consensus. Stages 2 and 3 were held in Workshop format in virtual mode (W) Results Stage 1- Of the total 20 Google forms sent to the AU, 13 responses were received: 7 from National Universities and 6 from Private Universities. All participants agreed to be part of the consensus. Stage 2- W: 20 representatives from 10 AU participated. It began with a contextualizing conference, after which the representatives were divided into 5 groups to assess the agreements of each D. Stage 3- The Cariology Curriculum document was organized into 5 Domains, and 23 C and 31 I of clinical application were defined for teaching cariology. The contents and competences for each domain were agreed upon. The final document was sent to all W participants for their approval and dissemination in each AU involved Conclusion Cariology contents were defined for dentistry students at Universities in the Argentine Republic.
RESUMEN Objetivo Elaborar un documento de consenso de los contenidos y competencias de cariología en el currículo para las facultades/escuelas de odontología argentinas, a nivel del grado Materiales y Método El proceso de creación se efectuó en etapas: 1- Diagnóstico de situación (Formulario electrónico) e invitación a participar a las 20 unidades académicas (UA) donde se imparte la carrera de odontología. 2- Proceso de valoración de acuerdos de Contenidos (C) y Competencias (I) en los cinco dominios (D): D1: Ciencias Básicas; D2: Riesgo y diagnóstico de caries dental; D3: Toma de decisiones tratamientos no invasivos; D4: Toma de decisiones para el tratamiento invasivo y D5: Cariología basada en la evidencia a nivel comunitario. 3- Etapa de consenso. Las etapas 2 y 3 se efectuaron en formato de Workshop en modalidad virtual (W) Resultados Etapa 1: Del total de 20 formularios enviados a las UA se recibieron 13 respuestas (65%), 7 (53,8%) de Universidades Nacionales y 6 (46,1%) de gestión Privada. El 100% de los participantes estuvieron de acuerdo en formar parte del consenso. Etapa 2: W: Participaron 20 representantes de 10 UA. El proceso se inició con una conferencia contextualizadora, posteriormente los representantes fueron divididos en 5 grupos para la valoración de acuerdos de cada D. Etapa 3: El documento de658. 658.l Currículo en Cariología se organizó en 5 Dominios. Se definieron 23 C y 31 I de aplicación clínica para la enseñanza de la Cariología. Se consensuaron los contenidos y las competencias para cada uno de los dominios. El documento final fue enviado a todos los participantes del W para su aprobación y difusión en cada una de las UA involucradas Conclusión En base al trabajo realizado se determinó un consenso de competencias y contenidos en cariología para estudiantes de grado de Odontología, de las Universidades de la República Argentina.
RESUMO
Objectives To evaluate the predictive significance of tumour size in patients undergoing curative surgery for colorectal cancer (CRC). Methods All patients undergoing curative surgery for colon or rectum cancer performed by a single colorectal surgeon between January 2013 and January 2020 were considered eligible for inclusion. Linear and binary logistic regression analyses were modelled to assess whether colonic or rectal tumour size could predict R0 resection, specimen length, number of harvested and positive lymph nodes, lymphocytic infiltration, venous invasion, and overall survival. Results A total of 192 patients were eligible for inclusion. In patients with colon cancer, tumour size was the independent predictor of the number of harvested lymph nodes (P<0.001), the number of positive lymph nodes (P=0.001), and lymphocytic infiltration (P=0.009). However, it did not predict R0 resection (P=0.563), specimen length (P=0.111), specimen length >120 mm (P=0.186), >12 harvested lymph nodes (P=0.145), venous invasion (P=0.103), and five-year overall survival (P=0.543). In patients with rectal cancer, tumour size was the independent predictor of the number of harvested lymph nodes (P<0.001) and the number of positive lymph nodes (P<0.001). However, it did not predict R0 resection (P=0.108), specimen length (P=0.774), specimen length >120 mm (P=0.405), >12 harvested lymph nodes (P= 0.069), lymphocytic infiltration (P=0.912), venous invasion (P= 0.105), and five-year overall survival (P=0.413). Conclusions The results of the current study suggest that tumour size on its own may not have a significant predictive value in oncological or survival outcomes in patients undergoing curative surgery for colon or rectum cancer.
RESUMO
Mycophenolate mofetil (MMF) is used extensively for the induction therapy of lupus nephritis (LN) and has even outpaced intravenous (i.v.) cyclophosphamide (CyP) as the initial choice of therapy. There are no studies comparing the response of MMF with standard dose i.v. CyP in Indian patients with LN. We conducted a 24-week prospective, randomized, open-label trial comparing oral MMF with monthly i.v. CyP as induction therapy for active biopsy proven Class III and IV LN. The primary end-point was response to treatment at 24 weeks, and the secondary end-points were complete remission, Systemic Lupus Erythematosus Disease Activity Index scores (SLEDAI) and adverse reactions. Of the 40 patients, 17 were randomized to the MMF group and 23 to the i.v. CyP group. Complete remission was seen in nine (52.94%) patients in the MMF group and 11 (47.82%) in the i.v. CyP group. Partial remission was seen in six (35.30%) in the MMF group and nine (39.13%) in the i.v. CyP group. At six months, the cumulative probability of response was not statistically significant between the two groups (P = 1.000). MMF is comparable to i.v. CyP in the management of LN in Indian patients having an equal safety profile. The dose of MMF required was lower than the conventional doses used in other studies suggesting genetic or environmental factors in the Indian population influencing the metabolism of MMF, which requires further evaluation. The cost of MMF is a limiting factor in its use. The use of i.v. CyP is favorable as the monthly doses ensure compliance and is also cost-effective.